Experiencing KEEL software: Application to fatigue data segment classification

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Most researchers have doubts over what type of classification model is most suitable for representing their data when applying a data mining approach. However, this quandary can be solved by performing a comparison between the available models. Generating multiple classification models simultaneously is cost-effective when using free data mining tools such as KEEL (Knowledge Extraction based on Evolutionary Learning). KEEL is an interactive data mining software that provides a high level of functionality for users. This paper presents an experience of using this user-friendly software to solve a fatigue data segment classification problem. The problem concerns classifying fatigue data segments whether they consist of low or high damage. Experiments over the dataset using three different types of classification algorithms (i.e. CN2, C4.5 and Naïve-Bayes), two discretization methods, and two filter-type feature selection methods show that there is no optimal classification algorithm in terms of indexing performance for our specific problem. Interestingly, however, this study does provide minor evidence that classifier performance could be increased by pairing discretization and feature selection methods appropriately.

Original languageEnglish
Title of host publicationAIP Conference Proceedings
PublisherAmerican Institute of Physics Inc.
Pages1178-1182
Number of pages5
Volume1605
ISBN (Print)9780735412415
DOIs
Publication statusPublished - 2014
Event21st National Symposium on Mathematical Sciences: Germination of Mathematical Sciences Education and Research Towards Global Sustainability, SKSM 21 - Penang
Duration: 6 Nov 20138 Nov 2013

Other

Other21st National Symposium on Mathematical Sciences: Germination of Mathematical Sciences Education and Research Towards Global Sustainability, SKSM 21
CityPenang
Period6/11/138/11/13

Fingerprint

data mining
learning
computer programs
classifiers
classifying
damage
costs
filters

Keywords

  • data mining classification
  • discretization
  • fatigue data segment
  • feature selection
  • KEEL software

ASJC Scopus subject areas

  • Physics and Astronomy(all)

Cite this

Osman, M. H. (2014). Experiencing KEEL software: Application to fatigue data segment classification. In AIP Conference Proceedings (Vol. 1605, pp. 1178-1182). American Institute of Physics Inc.. https://doi.org/10.1063/1.4887757

Experiencing KEEL software : Application to fatigue data segment classification. / Osman, Mohd Haniff.

AIP Conference Proceedings. Vol. 1605 American Institute of Physics Inc., 2014. p. 1178-1182.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Osman, MH 2014, Experiencing KEEL software: Application to fatigue data segment classification. in AIP Conference Proceedings. vol. 1605, American Institute of Physics Inc., pp. 1178-1182, 21st National Symposium on Mathematical Sciences: Germination of Mathematical Sciences Education and Research Towards Global Sustainability, SKSM 21, Penang, 6/11/13. https://doi.org/10.1063/1.4887757
Osman MH. Experiencing KEEL software: Application to fatigue data segment classification. In AIP Conference Proceedings. Vol. 1605. American Institute of Physics Inc. 2014. p. 1178-1182 https://doi.org/10.1063/1.4887757
Osman, Mohd Haniff. / Experiencing KEEL software : Application to fatigue data segment classification. AIP Conference Proceedings. Vol. 1605 American Institute of Physics Inc., 2014. pp. 1178-1182
@inproceedings{73462f7b8a294de7bcc0aa5ab2062192,
title = "Experiencing KEEL software: Application to fatigue data segment classification",
abstract = "Most researchers have doubts over what type of classification model is most suitable for representing their data when applying a data mining approach. However, this quandary can be solved by performing a comparison between the available models. Generating multiple classification models simultaneously is cost-effective when using free data mining tools such as KEEL (Knowledge Extraction based on Evolutionary Learning). KEEL is an interactive data mining software that provides a high level of functionality for users. This paper presents an experience of using this user-friendly software to solve a fatigue data segment classification problem. The problem concerns classifying fatigue data segments whether they consist of low or high damage. Experiments over the dataset using three different types of classification algorithms (i.e. CN2, C4.5 and Na{\"i}ve-Bayes), two discretization methods, and two filter-type feature selection methods show that there is no optimal classification algorithm in terms of indexing performance for our specific problem. Interestingly, however, this study does provide minor evidence that classifier performance could be increased by pairing discretization and feature selection methods appropriately.",
keywords = "data mining classification, discretization, fatigue data segment, feature selection, KEEL software",
author = "Osman, {Mohd Haniff}",
year = "2014",
doi = "10.1063/1.4887757",
language = "English",
isbn = "9780735412415",
volume = "1605",
pages = "1178--1182",
booktitle = "AIP Conference Proceedings",
publisher = "American Institute of Physics Inc.",

}

TY - GEN

T1 - Experiencing KEEL software

T2 - Application to fatigue data segment classification

AU - Osman, Mohd Haniff

PY - 2014

Y1 - 2014

N2 - Most researchers have doubts over what type of classification model is most suitable for representing their data when applying a data mining approach. However, this quandary can be solved by performing a comparison between the available models. Generating multiple classification models simultaneously is cost-effective when using free data mining tools such as KEEL (Knowledge Extraction based on Evolutionary Learning). KEEL is an interactive data mining software that provides a high level of functionality for users. This paper presents an experience of using this user-friendly software to solve a fatigue data segment classification problem. The problem concerns classifying fatigue data segments whether they consist of low or high damage. Experiments over the dataset using three different types of classification algorithms (i.e. CN2, C4.5 and Naïve-Bayes), two discretization methods, and two filter-type feature selection methods show that there is no optimal classification algorithm in terms of indexing performance for our specific problem. Interestingly, however, this study does provide minor evidence that classifier performance could be increased by pairing discretization and feature selection methods appropriately.

AB - Most researchers have doubts over what type of classification model is most suitable for representing their data when applying a data mining approach. However, this quandary can be solved by performing a comparison between the available models. Generating multiple classification models simultaneously is cost-effective when using free data mining tools such as KEEL (Knowledge Extraction based on Evolutionary Learning). KEEL is an interactive data mining software that provides a high level of functionality for users. This paper presents an experience of using this user-friendly software to solve a fatigue data segment classification problem. The problem concerns classifying fatigue data segments whether they consist of low or high damage. Experiments over the dataset using three different types of classification algorithms (i.e. CN2, C4.5 and Naïve-Bayes), two discretization methods, and two filter-type feature selection methods show that there is no optimal classification algorithm in terms of indexing performance for our specific problem. Interestingly, however, this study does provide minor evidence that classifier performance could be increased by pairing discretization and feature selection methods appropriately.

KW - data mining classification

KW - discretization

KW - fatigue data segment

KW - feature selection

KW - KEEL software

UR - http://www.scopus.com/inward/record.url?scp=84904697481&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84904697481&partnerID=8YFLogxK

U2 - 10.1063/1.4887757

DO - 10.1063/1.4887757

M3 - Conference contribution

AN - SCOPUS:84904697481

SN - 9780735412415

VL - 1605

SP - 1178

EP - 1182

BT - AIP Conference Proceedings

PB - American Institute of Physics Inc.

ER -